---
category: [Administration & Integrations, Platform and Product Extensions, Platform and Product Extensions/Integration, Administration & Integrations/Custom Integrations & Apps, Platform and Product Extensions/Workday Extend]
nav: wcp_docs
parent_url: /wcp_docs/
title: Skill Inference REST API
layout: subsection
---

## <a id="section_20"></a>Overview

The Skill Inference REST API infers the top skills that a person is likely to have learned from that experience or is likely to possess within that role. The Skill Inference API currently supports these types of experience input:

-   Job titles.
-   Academic degrees.
-   Professional certifications or licenses.


Using the Skill Inference API with the Skill Extract API, you can derive skills when there's sparse information about a worker, like an empty job profile. You can also augment skill data in cases where the job title, degree, or other experience conveys information about skills. Example: Candidates and workers often rely on titles and experience credentials to convey a baseline set of skills. In cases where candidates don't highlight relevant skills within the text of their resume or profile, the Skill Inference API can extract the skills.

Sample use cases:

-   As a people manager, you want to understand what skills your team members have that they might not have explicitly described on their profiles.

    You can use the Skill Inference API to pass job titles from past work experience, education, or certification. The Skill Inference API returns a list of skills that they're likely to have.

-   As a student, you want to understand what top skills are necessary for a specific job title.

    You can use the Skill Inference API to pass in the title of <i>Commercial Real Estate Paralegal</i> and understand what skills you might need to pursue that career path. These skills might include <i>Commercial Real Estate</i>, <i>Real Estate Law</i>, <i>Estate Disputes</i>, <i>Reviewing Contracts</i>, <i>Contract Writing</i>, and others.



## <a id="section_urlBasePath"></a>URL

```
https://api.workday.com/ml/skills-cloud/{version}/infer
```

For regional URL base paths, see [Reference: Workday Extend API Gateways and Authorization Base URLs](/wcp_docs/dlh1653340161856.html).

## <a id="section_inferringSkills"></a>Inferring Skills

To infer skill information from a given job title, academic degree, or certification, call this endpoint:

```
POST {baseURL}/infer
```

In the request body, specify these required fields:

-   `input_type` - The type of input text. Valid values:

    -   `certification`
    -   `education`
    -   `job_title`

-   `text` - The text to infer skills from. Maximum length is 200 characters.


To get the relevance score for each inferred skill, set the`include_relevance_score` request field to true. The relevance score is a measure of how relevant a skill is to the input context, ranging from zero to 1. A score of 1 indicates the highest relevance. Use scores only to compare the relative relevance of the results within a given API response. The API doesn't calibrate scores; don't use the scores for thresholding or comparison across APIs as they might change over time and across models. Furthermore, the effective range of the scores might vary. Example: the range of low to high relevance results could be 0.4 to 0.9 depending on the model.

The default is the English language and`en_US` locale for both the input text and output skills. If the input text needs to use a different locale, specify the `input_locale` request field. If the output skills need to use a different output locale, specify the `output_locale` request field. For valid locale code values, see [Reference: Skills Cloud Locales](/wcp_docs/GUID-b3c75508-018f-4cce-9d4d-9718cf5dfc69-enHYPHENus.html).

This sample request infers skills from a given job title:

```
POST https://api.workday.com/ml/skills-cloud/v2/infer
```

Sample request body:

```
{"input_type": "job_title",
"text": "Machine Learning Engineer"}
```

Sample response:

```
{
"data": [
{
  "relevance_score": 0.9161,
  "skill": {
    "id": "REMOTE_SKILL-1-119486",
    "name": "Python (Programming Language)",
    "locale": "en_US",
    "category": null,
    "description": {
      "text": "Python is a high-level, interpreted programming language that emphasizes readability with its notable use of significant whitespace. Being knowledgeable in Python may involve understanding its syntax, being able to write clean and efficient code, and having familiarity with Python's standard library as well as popular frameworks and libraries like Django, Flask, and Pandas. A professional skilled in Python can help an organization with tasks such as web and software development, data analysis and visualization, machine learning, and automation of repetitive tasks."
    },
    "is_maintained": false
  }
},
{
  "relevance_score": 0.9121,
  "skill": {
    "id": "REMOTE_SKILL-1-32353",
    "name": "Deep Learning",
    "locale": "en_US",
    "category": null,
    "description": {
      "text": "Deep Learning is a subset of machine learning that utilizes artificial neural networks with multiple layers, also known as deep neural networks, to model and understand complex patterns in datasets. Being knowledgeable in Deep Learning may involve understanding and implementing various types of neural networks, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), as well as mastering programming languages like Python and tools like TensorFlow or PyTorch. A professional skilled in Deep Learning can help an organization with tasks such as image and speech recognition, natural language processing, customer segmentation, fraud detection, and developing recommendation systems, among other applications."
    },
    "is_maintained": false
  }
},
. . .
{
  "relevance_score": 0.7043,
  "skill": {
    "id": "REMOTE_SKILL-1-110122",
    "name": "Backpropagation",
    "locale": "en_US",
    "category": null,
    "description": {
      "text": "Backpropagation is a method used in artificial intelligence and machine learning that adjusts the weights of neurons in a neural network based on the error rate obtained in the previous epoch (iteration). Being knowledgeable in Backpropagation may involve understanding complex mathematical concepts, algorithms, and programming languages, as well as the ability to apply these skills to optimize neural networks. A professional skilled in Backpropagation can help an organization improve its predictive modeling, data analysis, and machine learning capabilities, enabling more accurate forecasting, decision-making, and automation of tasks."
    },
    "is_maintained": false
  }
}
]
}
```

## <a id="section_limitations"></a>Limitations

The Skill Inference API doesn't support maintained, external, or crowdsourced skills.